[prev in list] [next in list] [prev in thread] [next in thread] 

List:       freebsd-hackers
Subject:    Re: help w/panic under heavy load - 5.4
From:       Edwin <edwin () verolan ! com>
Date:       2005-07-24 22:59:40
Message-ID: 20050724225940.GA28529 () asx01 ! verolan ! com
[Download RAW message or body]

Max Laier (max@love2party.net) wrote:
> 
> Edwin, what do you have for CFLAGS?  Can you try to downgrade to "-O" for now 
> so that we have a better chance to get a full view?
> 

Max, 

I have no CFLAGS or COPTFLAGS in /etc/make.conf - this was a basic
kern-developer install on a blank PC. The only thing that's a little 
different about the box that i use to compile is that it's a dual
processor machine - but no -j# options used in compilation of the kernel.

the compile is proceding with the following as an example output 
from make/cc

$ grep netinet /tmp/make.DEBUG1.output |grep fastfwd
cc -c -O -pipe  -Wall -Wredundant-decls -Wnested-externs -Wstrict-prototypes  \
                -Wmissing-prototypes -Wpointer-arith 
-Winline -Wcast-qual  -fformat-extensions -std=c99 -g -nostdinc -I-  -I. \
-I/usr/src/sys -I/usr/src/sys/contrib/dev/ acpica -I/usr/src/sys/contrib/altq \
                -I/usr/src/sys/contrib/ipfilter -I/usr/src/sys/contrib/pf \
                -I/usr/src/sys/contrib
/dev/ath -I/usr/src/sys/contrib/dev/ath/freebsd -I/usr/src/sys/contrib/ngatm \
-I/usr/src/sys/dev/twa -D_KERNEL -incl ude opt_global.h -fno-common \
-finline-limit=8000 --param inline-unit-growth=100 --param large-function-growth=1000 \
                
 -mno-align-long-strings -mpreferred-stack-boundary=2  -mno-mmx -mno-3dnow -mno-sse \
-mno-sse2 -ffreestanding -Werror  /usr/src/sys/netinet/ip_fastfwd.c $ 

are you referring to the -fformat-extensions, -fno-common and -finline...etc
optimizations as well? or just the -O v. -O2/-O3/-Os one? 

If yes to the -f* optimizations - besides commenting out parts of the makefiles
- is there a 'normal' way to disable them?

FWIW - I also had (I think) the same problem with the 5.3 release - but I 
never worked it out - just other things on my plate, so I don't believe it's
a recent code change (ie. 5.4 timeframe) if it does turn out to be a code 
change.

it also has something to do with the load on the box - I'm testing with
small udp packets (using iperf) - if I step up the size - I have to step
up the bandwidth in order to cause the panic. 


_______________________________________________
freebsd-hackers@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hackers
To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.org"


[prev in list] [next in list] [prev in thread] [next in thread]